productivity▌

基于 lark-cli 创建新 Skill。Skill = 一份 SKILL.md，教 AI 用 CLI 命令完成任务。

Autonomously research new technologies from the web and generate reusable agent skills. \n \n Discovers authoritative documentation via web search, prioritizing official docs, GitHub repositories, and blogs \n Extracts installation, core concepts, API references, and code examples from 3–5 high-quality sources \n Generates a self-contained skill with YAML frontmatter, markdown instructions, and optional bundled resources (scripts, references, assets) \n Saves skills to workspace-specific or glob

Add educational comments to code files to transform them into effective learning resources. \n \n Adapts explanation depth and tone to three configurable knowledge levels: beginner, intermediate, and advanced \n Automatically requests a file if none is provided, with numbered list matching for quick selection \n Expands files by up to 125% using educational comments only (hard limit: 400 new lines; 300 for files over 1,000 lines) \n Preserves file encoding, indentation style, syntax correctness,

This is a Level 7 (self-improving) skill. It has two distinct sections:

Techniques and patterns for crafting effective prompts across LLMs, image generators, and video models. \n \n Covers LLM prompting fundamentals: role assignment, task clarity, chain-of-thought reasoning, few-shot examples, output format specification, and constraint setting \n Image generation structure includes subject description, style keywords, composition control, quality modifiers, and negative prompt usage \n Video prompting guidance covers shot types, camera movement, action description,

Structured competitive analysis with feature matrices, pricing breakdowns, SWOT analysis, and positioning maps. \n \n Provides a 7-layer analysis framework covering product, pricing, positioning, traction, reviews, content, and team across competitors \n Includes templates and commands for feature matrices, pricing comparisons, SWOT analysis, and 2x2 positioning maps with visual generation \n Integrates web search (Tavily, Exa), browser automation for UX screenshots, and Python for positioning m

Structured prompt for generating Epic-level Product Requirements Documents with consistent output format. \n \n Guides product managers through a standardized PRD structure covering goals, user personas, journeys, functional and non-functional requirements, success metrics, and scope boundaries \n Outputs markdown-formatted PRDs saved to a consistent directory path ( /docs/ways-of-work/plan/{epic-name}/epic.md ) for use as single source of truth \n Includes built-in prompting for clarifying ques

Writes an explicit entry to auto-memory when something is important enough that you don't want to rely on Claude noticing it automatically.

Analyzes git changes and creates semantic Git Flow branches automatically based on change type. \n \n Inspects staged and unstaged changes via git status and git diff to determine branch category: feature, release, or hotfix \n Generates semantic branch names following Git Flow conventions (e.g., feature/user-auth , release-1.2.0 , hotfix/security-patch ) \n Branches from the correct source ( develop for features and releases, master for hotfixes) and creates the branch in one command \n Handles

Automated Azure Verified Module version updates for Bicep files with breaking change detection. \n \n Scans Bicep files to extract AVM module references, queries MCR for latest versions, and applies updates automatically \n Pauses for manual approval when breaking changes, security modifications, or parameter incompatibilities are detected \n Validates all changes with bicep lint and bicep build to ensure compliance before finalizing \n Outputs results in a structured table showing module names,